Logistics robots think ahead
Jacobs University participates in the European Integrated Project RobLog (Cognitive Robot for Automation of Logistic Processes) on robotics development for logistics processes. Funded for a four-years-period with a total budget of 7,86 million Euros by the European Union, five European research teams and two companies join forces for the research project on cognitive systems and robotics. The Jacobs scientists under the lead of professor Andreas Birk receives 1,42 million Euros of the project money to contribute the robots' 3D perception in challenging scenarios. The project starts on February 1, 2011.
January 31, 2011One consequence of globalization is an increased transport of goods. Nowadays, most goods are shipped in containers and are transferred onto trucks for further transport. The containers are unloaded manually since they are nearly always packed chaotically, the variety of transported goods is high, and time requirements are strict. Unloading of containers is a strenuous task as goods have a weight up to 70 kg that poses health risks, which include the effects of pesticides and poisonous gases as well as injuries through unexpectedly falling objects. Human labor is hence a high cost factor combined with unhealthy working conditions, making automated solutions highly desirable.
Existing systems for automated unloading are restricted to specific scenarios and still have drawbacks in their flexibility, adaptability and robustness. A robotic system suited for any unloading task of containers requires a high amount of cognitive capabilities. A key element for automation in these challenging application scenarios is 3D perception modeling. “Perception is a complex process. Not only the objects themselves, but also their physical properties have to be recognized. The robot has to correctly assess the whole scene to be capable to make the right decisions in realtime” explain Andreas Birk, Jacobs Professor of Computer Science and Electrical Engineering. The Robolog system will not just simply be programmed by hand for this purpose, but it will be equipped with a significant amount of learning capabilities. Roblog will for example learn about new objects while executing its tasks and manage to recognize them under different conditions.
The Roblog system analysis the 3D appearance of objects, i.e., their shapes, colors, and textures, and combines them with measurements in the robot-arm and fingers during the manipulation. This allows the system to make conclusions about to be expected physical properties like weight, deformability or surface properties of previously encountered objects before having to touch them. This allows Roblog to build up and maintain a dynamic semantic 3D model of its working environment. This empowers the system with anticipation: the robot can forecast possible consequences of its actions, e.g., the undesired collapse of a pile of objects if the wrong one at a disadvantageous spot is removed.
All these advances are demonstrated within the project in close cooperation with an industrial end-user in a realistic application scenario; thus opening the potential to reach a completely new level of automation in the logistics chain.
The RobLog consortium includes reserach groups from Fachhochschule Reutlingen, Orebro University, Sweden, BIBA (Bremer Institut für Produktion und Logistik GmBH), Universita di Pisa, Italy, Qubiqa A/S, Denmark and Berthold Vollers GmbH, Bremen. Scientists and endusers will cooperate closely and thus meet all functional requirements. For automation in logistics this can mean entering a new area.
Further information on Jacobs research on Cognitive Systems and Processes (COSYP)
